CN117237155A - Intelligent campus student behavior analysis system based on artificial intelligence - Google Patents
Intelligent campus student behavior analysis system based on artificial intelligence Download PDFInfo
- Publication number
- CN117237155A CN117237155A CN202311410907.0A CN202311410907A CN117237155A CN 117237155 A CN117237155 A CN 117237155A CN 202311410907 A CN202311410907 A CN 202311410907A CN 117237155 A CN117237155 A CN 117237155A
- Authority
- CN
- China
- Prior art keywords
- data
- voice
- target area
- student
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 35
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 39
- 230000014509 gene expression Effects 0.000 claims description 24
- 238000000034 method Methods 0.000 claims description 24
- 230000000875 corresponding effect Effects 0.000 claims description 15
- 230000003542 behavioural effect Effects 0.000 claims description 5
- 230000002596 correlated effect Effects 0.000 claims description 5
- 230000008451 emotion Effects 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 239000003795 chemical substances by application Substances 0.000 claims 3
- 239000003550 marker Substances 0.000 claims 1
- 230000006378 damage Effects 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 34
- 238000010586 diagram Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000003445 biliary tract Anatomy 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 230000009323 psychological health Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Abstract
The application belongs to the technical field of student behavior analysis, and discloses an intelligent campus student behavior analysis system based on artificial intelligence, which comprises a data acquisition module, a data acquisition module and a data analysis module, wherein the data acquisition module is used for acquiring student information; the video acquisition module is used for acquiring monitoring video data of the campus; the video analysis module is used for analyzing the monitoring video data and judging whether a suspicious target area is generated, and if the suspicious target area is generated, voice acquisition information is generated; the voice acquisition module acquires voice data of the suspicious target area according to the voice acquisition information; the voice recognition module is used for recognizing voice data of the suspicious target area and judging whether a spoofing behavior statement exists or not; if campus spoofing behavior exists, determining an agent in real time, and according to student information corresponding to the determined agent, timely contacting by a executive owner according to contact ways corresponding to the student information, so as to timely refrain the behavior, avoid the behavior from causing greater harm to others, and effectively reduce occurrence of campus spoofing.
Description
Technical Field
The application relates to the technical field of student behavior analysis, in particular to an intelligent campus student behavior analysis system based on artificial intelligence.
Background
The prior application publication number CN110348754A discloses a campus tyrant behavior early warning system and method based on an artificial intelligence technology, comprising: each student is assigned a category coefficient K according to the daily performance of the student, the category coefficient K carries out assignment according to the daily performance of the student, the higher the probability of being subjected to the overlong is, the higher the assignment is, the higher the probability of being subjected to the overlong is, the smaller the assignment is, and the student terminal is provided with a fingerprint identification module, a camera module and a display screen module; when the device is in a overlooked state, the device can quickly alarm through the fingerprint identification module, so that the device is protected from being infringed.
However, the following drawbacks still exist in the prior art:
1. the hysteresis exists in both the discovery and the prevention of the action, and larger injuries already occur, so that the prevention effect is not ideal;
2. the students still need to actively alarm;
3. students may also be afraid of alarm due to small biliary tree and fear of being replied;
in view of the above, the application provides an artificial intelligence based intelligent campus student behavior analysis system to solve the above problems.
Disclosure of Invention
In order to overcome the defects in the prior art, the embodiment of the application provides an intelligent campus student behavior analysis system based on artificial intelligence.
In order to achieve the above purpose, the present application provides the following technical solutions:
an artificial intelligence based intelligent campus student behavior analysis system is applied to an artificial intelligence server and comprises:
the data acquisition module acquires student information;
the video acquisition module is used for acquiring monitoring video data of the campus;
the video analysis module is used for analyzing the monitoring video data and judging whether a suspicious target area is generated, and if the suspicious target area is generated, voice acquisition information is generated;
the voice acquisition module acquires voice data of the suspicious target area according to the voice acquisition information;
and the voice recognition module is used for recognizing the voice data of the suspicious target area, judging whether a spoofing behavior statement exists, extracting voiceprint data of the voice data if the spoofing behavior statement exists, and determining n agents according to the voiceprint data.
Further, the student information comprises identity information and voiceprint data, the identity information at least comprises an identity card number, and the student information is collected at each learning period and uploaded to a database in an artificial intelligent server for storage;
the monitoring video data is obtained through a camera installed in a public area where campus spoofing is easy to occur in the campus.
Further, the method for determining whether to generate the suspicious target area comprises the following steps:
analyzing the monitoring video data frame by frame, and identifying the number of people in each frame of picture through a personnel identification model;
and (3) suspicious marking is carried out on the area where w persons with the personnel distance smaller than the preset distance are located in the frame picture, and the area where the suspicious mark is located and the duration time of which is longer than the preset duration time threshold is marked as a suspicious target area.
Further, the method for obtaining the duration of the region where the suspicious mark is located comprises the following steps:
s= (Z-1) ×t, S is the duration of the region where the suspicious mark is located, Z is the number of frame images of the region where w persons having a person distance smaller than a preset distance are located, and T is the interval duration of the frame images.
Further, the voice acquisition information includes coordinate data of the suspicious target area.
Further, the method for acquiring the voice data of the suspicious target area comprises the following steps:
the voice acquisition modules are installed in one-to-one correspondence with the positions of the video acquisition modules, each voice acquisition module comprises a steering engine module and a remote acquisition sound module connected with the steering engine module, and the steering engine module controls the pointing direction of the remote acquisition sound module according to the coordinate data of the suspicious target area to remotely acquire the voice data of the suspicious target area.
Further, the method for determining whether the deceptive behavior statement exists comprises the following steps:
and converting the voice data of the suspicious target area into identification characters, comparing the pre-stored identification characters with the identification characters in the database, and if the identification characters consistent with the identification characters exist, judging that the identification characters exist, wherein the identification characters exist.
Further, the method for determining n agents according to the voiceprint data comprises the following steps:
comparing the voiceprint data of the extracted voice data with voiceprint data prestored in a database, determining student information according to the voiceprint data consistent with the comparison, and determining an agent according to the determined student information; the number of students involved is determined based on the number of voiceprint data from which the voice data was extracted.
Further, the method further comprises an expression recognition model, the expression recognition model analyzes the monitoring video data corresponding to the voice print statement frame by frame, and if the voice print statement exists, student information is determined according to the voice print data.
Further, the system also comprises an equipment linkage module, wherein the equipment linkage module correlates the installation direction positions of the video acquisition modules, the correlated video acquisition modules are at least positioned in r different directions of the same monitoring area, and r is an integer larger than 1;
if the deception behavior statement exists, the device linkage module enables the rest video acquisition modules in the r monitoring video data of the suspicious target area, and the r monitoring video data are correlated to be the monitoring video data corresponding to the deception behavior statement.
The intelligent campus student behavior analysis system based on artificial intelligence has the technical effects and advantages that: determining suspicious target area by monitoring video data, acquiring suspicious target area voice data, converting voice data into identification words, judging whether there is identification words consistent with the spoofing words, determining whether there is campus spoofing, if there is campus spoofing, determining agent in real time, according to student information corresponding to the agent, timely contacting by a executive according to contact mode corresponding to student information, the method has timeliness and better stopping effect, and can effectively control the behavior of the ice in the campus, thereby being beneficial to building a good campus environment and maintaining the psychological health of students.
Drawings
FIG. 1 is a schematic diagram of an intelligent campus student behavior analysis system based on artificial intelligence in embodiment 1 of the application;
FIG. 2 is a schematic diagram of an artificial intelligence based intelligent campus student behavior analysis method;
FIG. 3 is a schematic diagram of an electronic device according to the present application;
FIG. 4 is a schematic diagram of an intelligent campus student behavior analysis system based on artificial intelligence in embodiment 2 of the application;
FIG. 5 is a schematic diagram of an intelligent campus student behavior analysis system based on artificial intelligence according to embodiment 3 of the present application;
FIG. 6 is a schematic diagram of a voice acquisition module according to the present application;
fig. 7 is a schematic diagram of an expression recognition model training method according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Example 1
Referring to fig. 1, the intelligent campus student behavior analysis system based on artificial intelligence of the present embodiment is applied to an artificial intelligence server, and includes a data acquisition module, a video analysis module, a voice acquisition module and a voice recognition module, where the modules are connected by wires and/or wirelessly to realize data transmission between the modules.
The data acquisition module is used for acquiring student information, the student information comprises identity information and voiceprint data, the identity information at least comprises an identity card number, the student information can be acquired when the student is in study in every learning period, and the student information is uploaded to a database in the artificial intelligent server for storage.
The video acquisition module is used for acquiring the monitoring video data of the campus and sending the monitoring video data to the video analysis module; the video acquisition module is used for acquiring cameras which are arranged in each public area in the campus and are easy to generate campus spoofing;
the video analysis module is used for analyzing the monitoring video data, judging whether a suspicious target area is generated, generating voice acquisition information if the suspicious target area is generated, and sending the voice acquisition information to the corresponding voice acquisition module;
the method for judging whether to generate the suspicious target area comprises the following steps:
analyzing the monitoring video data frame by frame, and identifying the number of people in each frame of picture through a personnel identification model;
the method comprises the steps that suspicious marking is carried out on an area where w persons with the personnel distance smaller than a preset distance are located in a frame picture, the area where the suspicious marking is located is marked as a suspicious target area, the duration time of the area where the suspicious marking is located is longer than a preset duration time threshold, in an embodiment, the area where the suspicious marking is located is an aggregation area, the value range of the preset distance is 50cm-60cm, the duration time threshold is preset, and the time of the suspicious marking is longer than 1 minute;
the personnel distance in the frame picture is calculated according to the boundary frame by detecting the boundary frame of each personnel in the video frame picture through the existing target detection algorithm (such as YOLO, SSD, fast R-CNN and the like) based on deep learning, the distance can be calculated through euclidean distance, mahalanobis distance or other distance measures, and the personnel identification model is obtained by adopting the existing computer vision model in the camera.
The method for obtaining the duration of the region where the suspicious mark is located comprises the following steps:
s= (Z-1) ×t, S is the duration of the region where the suspicious mark is located, Z is the number of frame images of the region where w persons having a person distance smaller than a preset distance are located, and T is the interval duration of the frame images.
The voice acquisition information includes coordinate data of the suspicious target area, which may be determined from the suspicious target area, for example, first scene measurement:
placing reference objects or calibration plates of known dimensions in the monitored area to measure the pixel coordinates and actual physical coordinates of these objects in the monitored video; establishing a mapping relation between the pixel coordinates and the actual physical coordinates through the known pixel coordinates and the actual physical coordinates;
coordinate system conversion:
establishing a conversion relation between a pixel coordinate system and an actual physical coordinate system by using the camera calibration and scene measurement results; converting pixel coordinates in the monitoring video into actual physical coordinates, thereby establishing a plane coordinate system, and extracting coordinate data of a suspicious target area through the established plane coordinate system;
the coordinate data of the suspicious target area can also be obtained through a radar module which is installed together with the camera.
The voice acquisition module is started according to the voice acquisition information, acquires voice data of the suspicious target area, and sends the voice data of the suspicious target area to the voice recognition module;
the method for acquiring the voice data of the suspicious target area comprises the following steps:
referring to fig. 6, the corresponding voice acquisition modules are installed in one-to-one correspondence with the positions of the video acquisition modules, the voice acquisition modules comprise remote acquisition voice modules connected with the steering engine modules, the steering engine modules control the pointing direction of the remote acquisition voice modules according to the coordinate data of the suspicious target area, and remotely acquire the voice data of the suspicious target area;
in this embodiment, the remote sound acquisition module uses an existing laser sound acquisition device or other devices capable of remotely acquiring sound, taking the laser sound acquisition device as an example, by emitting an infrared laser beam to an object in a suspicious target area, when the laser beam irradiates the surface of the object, the object vibrates (for example, vibration caused by sound) on the surface of the object, and the surface of the object can undergo tiny displacement; the vibration of the surface of the object causes the phase or intensity of the reflected light of the light beam to change slightly; an optical sensor or optical detector is then used to detect the change in the reflected laser beam; finally, sound reduction:
by analyzing the detected change of the optical signal, the laser sound acquisition device can restore the sound waveform, thereby obtaining the voice data of the suspicious target area.
And the voice recognition module is used for recognizing the voice data of the suspicious target area, judging whether a spoofing behavior statement exists, extracting voiceprint data of the voice data if the spoofing behavior statement exists, and determining n agents according to the voiceprint data.
The method for judging whether the deceptive behavior statement exists comprises the following steps:
the voice data of the suspicious target area is converted into identification characters, the pre-stored identification characters in the database are compared, if the identification characters consistent with the identification characters exist, the existence of the identification characters is judged, and the identification characters are exemplified as follows: give money, teach you, listen to my words, find people, beat you, etc.
The method for determining student information according to voiceprint data comprises the following steps:
comparing the voiceprint data of the extracted voice data with voiceprint data prestored in a database, determining student information according to the voiceprint data consistent with the comparison, and determining an agent according to the determined student information; n is determined based on the number of voiceprint data of the extracted voice data.
According to the method, the suspicious target area is determined through monitoring video data, then voice data of the suspicious target area are obtained, the voice data are converted into identification words, whether the identification words consistent with the spoofing words exist or not is judged, if the campus spoofing behaviors exist, agents are determined in real time, according to student information corresponding to the agents, the agents can be timely contacted by a executive according to contact modes corresponding to the student information, the agents are timely restrained, the agents are prevented from causing greater harm to the others, the occurrence of the campus spoofing is effectively reduced, timeliness is achieved, the restraining effect is better, meanwhile, the ideological education of the schools is enhanced for the agents, the occurrence of the spoofing behaviors in the campus is effectively controlled, a good campus environment is facilitated to be built, and mental health of students is maintained.
Example 2
Referring to fig. 4, the design is further improved based on embodiment 1, when a suspicious target area appears in a monitoring area, the obtained voice data of the suspicious target area may be a fun among students when a deceptive behavior statement exists, how to improve the analysis accuracy of a student behavior analysis system, and the intelligent campus student behavior analysis system based on artificial intelligence further includes an expression recognition model;
and if the expression is in the presence of the deception behavior statement, analyzing the monitoring video data corresponding to the deception behavior statement frame by the expression recognition model, and if the expression is in the presence of the deception emotion, determining student information according to the voiceprint data.
Referring to fig. 7, the expression recognition model training method includes:
step 1, collecting facial expression sample data of a plurality of groups of the agents in advance,
step 2, dividing the sample data into a training sample set and a verification sample set according to the proportion of 8:2;
step 3, inputting the training sample set into an expression recognition model for training and obtaining a trained expression recognition model;
step 4, inputting the verification sample set into the trained expression recognition model to obtain an output value of the expression recognition model, and obtaining an error between a predicted label and an actual value through an actual label in the verification sample set;
step 5, judging whether the error is in the set range, if so, stopping training, otherwise, adjusting the weight and the bias of the expression recognition model according to the obtained error, and returning to the step 3 to continue training; expression recognition models such as Convolutional Neural Networks (CNNs), labels such as anger, sadness, or fear, and the like.
According to the embodiment, the facial expression sample data of a plurality of groups of the agents are collected in advance, the expression recognition model is trained, then the expression recognition model is trained, when the voice data of the suspicious target area exist, the monitoring video data corresponding to the existence of the anti-ice action sentences are analyzed frame by frame, the running memory of the artificial intelligent server can be reduced, if the anti-ice emotion expression exists, student information is determined according to the voiceprint data, accuracy of the system on agent recognition is further improved, probability of false recognition is reduced, and occurrence of anti-ice actions is better prevented.
Example 3
Referring to fig. 5, since the surveillance video data is acquired by a single camera, when a suspicious target area appears, the personnel distribution is mostly in a ring shape, for example, a plurality of students surround one student, and when the surveillance video data acquired by the single camera is analyzed, it is difficult to comprehensively analyze the expressions of all participants when the expression recognition model analyzes the surveillance video data corresponding to the existence of the bloody behavioral sentence, that is, whether the expression is not comprehensive enough is determined; the embodiment is further improved on the basis of the embodiment 2, except that the intelligent campus student behavior analysis system based on artificial intelligence further comprises an equipment linkage module;
the equipment linkage modules are associated according to the installation direction positions of the video acquisition modules, the associated video acquisition modules are at least positioned in r different directions of the same monitoring area, r is an integer greater than 1, and r is preferably 4;
if the deception behavior statement exists, the device linkage module enables the rest video acquisition modules in the r monitoring video data of the suspicious target area, and the r monitoring video data are correlated to be the monitoring video data corresponding to the deception behavior statement.
According to the embodiment, r monitoring video data in different directions in the same monitoring area are added, and the r monitoring video data are correlated to be the monitoring video data corresponding to the existing deceptive behavior sentences, so that the expression of all participants is comprehensively analyzed by the system, and the accuracy of the system on the identification of the agents is further improved.
Example 4
Referring to fig. 2, the embodiment is not described in detail, but is partially described in embodiment one, and a smart campus online management method based on cloud computing is provided, where the method includes:
collecting student information;
collecting monitoring video data of a campus;
analyzing the monitoring video data, judging whether a suspicious target area is generated, and if so, generating voice acquisition information;
starting according to the voice acquisition information to acquire voice data of the suspicious target area;
and identifying the voice data of the suspicious target area, judging whether a deceptive behavior statement exists, if so, extracting voiceprint data of the voice data, and determining n agents according to the voiceprint data.
Example 5
Referring to fig. 3, the disclosure of the present embodiment provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the above-mentioned intelligent campus online management method based on cloud computing when executing the computer program.
Since the electronic device described in this embodiment is an electronic device used to implement the intelligent campus online management method based on cloud computing in the embodiment of the present application, based on the intelligent campus online management method based on cloud computing described in the embodiment of the present application, those skilled in the art can understand the specific implementation manner of the electronic device and various modifications thereof, so how to implement the method in the embodiment of the present application for this electronic device will not be described in detail herein. As long as the person skilled in the art implements the electronic device adopted by the intelligent campus online management method based on cloud computing in the embodiment of the application, the electronic device belongs to the scope of protection required by the application.
Example 6
Referring to FIG. 3, a computer readable storage medium having stored thereon a computer program that is erasable is shown according to an exemplary embodiment;
when the computer program runs on the computer equipment, the computer equipment is caused to execute the intelligent campus online management method based on cloud computing.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (10)
1. An artificial intelligence based intelligent campus student behavior analysis system, which is characterized by being applied to an artificial intelligence server and comprising:
the data acquisition module acquires student information;
the video acquisition module is used for acquiring monitoring video data of the campus;
the video analysis module is used for analyzing the monitoring video data and judging whether a suspicious target area is generated, and if the suspicious target area is generated, voice acquisition information is generated;
the voice acquisition module acquires voice data of the suspicious target area according to the voice acquisition information;
and the voice recognition module is used for recognizing the voice data of the suspicious target area, judging whether a spoofing behavior statement exists, extracting voiceprint data of the voice data if the spoofing behavior statement exists, and determining n agents according to the voiceprint data.
2. The intelligent campus student behavior analysis system based on artificial intelligence of claim 1, wherein the student information comprises identity information and voiceprint data, and the identity information at least comprises an identity card number;
the monitoring video data is obtained through a camera installed in a public area where campus spoofing is easy to occur in the campus.
3. The artificial intelligence based intelligent campus student behavior analysis system of claim 2, wherein the method for determining whether to generate the suspicious target area comprises:
analyzing the monitoring video data frame by frame, and identifying the number of people in each frame of picture through a personnel identification model;
and (3) suspicious marking is carried out on the area where w persons with the personnel distance smaller than the preset distance are located in the frame picture, and the area where the suspicious mark is located and the duration time of which is longer than the preset duration time threshold is marked as a suspicious target area.
4. The intelligent campus student behavior analysis system based on artificial intelligence of claim 3, wherein the suspicious marker location duration obtaining method comprises the following steps:
s= (Z-1) ×t, S is the duration of the region where the suspicious mark is located, Z is the number of frame images of the region where w persons having a person distance smaller than a preset distance are located, and T is the interval duration of the frame images.
5. An artificial intelligence based smart campus student behavioral analysis system according to claim 4 in which the speech acquisition information includes coordinate data of the suspicious target region.
6. The intelligent campus student behavior analysis system based on artificial intelligence of claim 5, wherein the method for acquiring voice data of suspicious target areas comprises the following steps:
the voice acquisition modules are installed in one-to-one correspondence with the positions of the video acquisition modules, each voice acquisition module comprises a steering engine module and a remote acquisition sound module connected with the steering engine module, and the steering engine module controls the pointing direction of the remote acquisition sound module according to the coordinate data of the suspicious target area to remotely acquire the voice data of the suspicious target area.
7. An artificial intelligence based intelligent campus student behavioral analysis system according to claim 6 wherein the method of determining whether there is a deceptive behavioral sentence comprises:
and converting the voice data of the suspicious target area into identification characters, comparing the pre-stored identification characters with the identification characters in the database, and judging that the illegal behavior sentences exist if the identification characters consistent with the illegal characters exist.
8. The artificial intelligence based intelligent campus student behavioral analysis system of claim 7, wherein the method of determining n agents from voiceprint data comprises:
extracting voiceprint data of voice data, comparing the voiceprint data with voiceprint data prestored in a database, determining student information according to the voiceprint data consistent with the comparison, and determining an agent according to the determined student information; the number of students involved is determined based on the number of voiceprint data from which the voice data was extracted.
9. The intelligent campus student behavior analysis system based on artificial intelligence of claim 1, further comprising an expression recognition model, wherein the expression recognition model analyzes the surveillance video data corresponding to the existence of the deceptive behavior sentence frame by frame, and if the existence of the deceptive emotion expression exists, the student information is determined according to the voiceprint data.
10. The intelligent campus student behavior analysis system based on artificial intelligence according to claim 9, further comprising an equipment linkage module, wherein the equipment linkage module is associated according to the installation direction positions of each video acquisition module, the associated video acquisition modules are at least positioned in r different directions of the same monitoring area, and r is an integer greater than 1;
if the deception behavior statement exists, the device linkage module enables the rest video acquisition modules in the r monitoring video data of the suspicious target area, and the r monitoring video data are correlated to be the monitoring video data corresponding to the deception behavior statement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311410907.0A CN117237155A (en) | 2023-10-28 | 2023-10-28 | Intelligent campus student behavior analysis system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311410907.0A CN117237155A (en) | 2023-10-28 | 2023-10-28 | Intelligent campus student behavior analysis system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117237155A true CN117237155A (en) | 2023-12-15 |
Family
ID=89084370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311410907.0A Pending CN117237155A (en) | 2023-10-28 | 2023-10-28 | Intelligent campus student behavior analysis system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237155A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104468981A (en) * | 2014-11-14 | 2015-03-25 | 哈尔滨工业大学 | School bullying detection method based on smart phone platform |
| CN110348754A (en) * | 2019-07-16 | 2019-10-18 | 郭俊雄 | A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology |
| CN110895861A (en) * | 2018-09-13 | 2020-03-20 | 杭州海康威视数字技术股份有限公司 | Abnormal behavior early warning method and device, monitoring equipment and storage medium |
| CN111738210A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Audio and video based student psychological state analysis method, device, terminal and medium |
| CN113205661A (en) * | 2021-04-30 | 2021-08-03 | 广东艾檬电子科技有限公司 | Anti-cheating implementation method and system, intelligent wearable device and storage medium |
| CN114821422A (en) * | 2022-04-24 | 2022-07-29 | 橙安(广东)信息技术有限公司 | Intelligent campus monitoring system and method for prejudging campus overlord |
| CN115273845A (en) * | 2022-07-27 | 2022-11-01 | 西安西古光通信有限公司 | Visual anti-cheating system, system operation method, device and medium |
-
2023
- 2023-10-28 CN CN202311410907.0A patent/CN117237155A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104468981A (en) * | 2014-11-14 | 2015-03-25 | 哈尔滨工业大学 | School bullying detection method based on smart phone platform |
| CN110895861A (en) * | 2018-09-13 | 2020-03-20 | 杭州海康威视数字技术股份有限公司 | Abnormal behavior early warning method and device, monitoring equipment and storage medium |
| CN110348754A (en) * | 2019-07-16 | 2019-10-18 | 郭俊雄 | A kind of campus despot's Ling Hangwei early warning system and method based on artificial intelligence technology |
| CN111738210A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Audio and video based student psychological state analysis method, device, terminal and medium |
| CN113205661A (en) * | 2021-04-30 | 2021-08-03 | 广东艾檬电子科技有限公司 | Anti-cheating implementation method and system, intelligent wearable device and storage medium |
| CN114821422A (en) * | 2022-04-24 | 2022-07-29 | 橙安(广东)信息技术有限公司 | Intelligent campus monitoring system and method for prejudging campus overlord |
| CN115273845A (en) * | 2022-07-27 | 2022-11-01 | 西安西古光通信有限公司 | Visual anti-cheating system, system operation method, device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10614310B2 (en) | Behavior recognition | |
| CN109598885B (en) | Monitoring system and alarm method thereof | |
| CN108154075A (en) | The population analysis method learnt via single | |
| JP2020507177A (en) | System for identifying defined objects | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN106960473B (en) | behavior perception system and method | |
| CN110231605B (en) | Human behavior recognition method and device, computer equipment and storage medium | |
| CN114973140A (en) | Dangerous area personnel intrusion monitoring method and system based on machine vision | |
| CN112364696A (en) | Method and system for improving family safety by using family monitoring video | |
| RU2018112646A (en) | SYSTEMS AND METHODS FOR LEARNING DETECTION TRAINING | |
| CN103500330A (en) | Semi-supervised human detection method based on multi-sensor and multi-feature fusion | |
| CN109657737A (en) | Toy intrusion detection method and system in a kind of cabinet based on the infrared thermovision technology of low cost | |
| JP2023546672A (en) | Rail feature identification system | |
| CN111344761A (en) | Vehicle exterior communication device, vehicle exterior communication method, information processing device, and vehicle exterior communication program | |
| CN108319892A (en) | A kind of vehicle safety method for early warning and system based on genetic algorithm | |
| CN112911204A (en) | Monitoring method, monitoring device, storage medium and electronic equipment | |
| Umoh et al. | Support vector machine-based fire outbreak detection system | |
| CN112288975A (en) | Event early warning method and device | |
| CN111027463A (en) | Wall turning detection method based on video analysis | |
| CN113392706A (en) | Device and method for detecting smoking and using mobile phone behaviors | |
| CN117237155A (en) | Intelligent campus student behavior analysis system based on artificial intelligence | |
| CN112183532A (en) | Safety helmet identification method based on weak supervision collaborative learning algorithm and storage medium | |
| CN115294709A (en) | Optical fiber vibration monitoring model, precaution system, electronic equipment and storage medium | |
| KR20200123324A (en) | A method for pig segmentation using connected component analysis and yolo algorithm | |
| CN113887634A (en) | Improved two-step detection-based electric safety belt detection and early warning method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |